Training in progress, epoch 1

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 8.89,
-    "total_flos": 5.786635923932774e+16,
-    "train_loss": 0.40318952401479086,
-    "train_runtime": 239.9675,
-    "train_samples_per_second": 10.876,
-    "train_steps_per_second": 0.25
+    "epoch": 13.33,
+    "total_flos": 8.682439554251366e+16,
+    "train_loss": 0.735786771774292,
+    "train_runtime": 315.7979,
+    "train_samples_per_second": 16.53,
+    "train_steps_per_second": 0.063
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69f851a3beb89215de6a9884c648d966377f0562bd7a380f10adb5c047d3c00b
+oid sha256:e2e9d9e17f5a4c9fee60b1ebd0ac2454794886ab0415946ad504881397c564d6
 size 110397937

runs/Jul20_18-21-11_7c542bce262c/events.out.tfevents.1689877415.7c542bce262c.12451.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c65a2627545d727c5000c3d1ab68ca05d04b7c7df720da08fef2cefabac966d1
+size 4834

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 8.89,
-    "total_flos": 5.786635923932774e+16,
-    "train_loss": 0.40318952401479086,
-    "train_runtime": 239.9675,
-    "train_samples_per_second": 10.876,
-    "train_steps_per_second": 0.25
+    "epoch": 13.33,
+    "total_flos": 8.682439554251366e+16,
+    "train_loss": 0.735786771774292,
+    "train_runtime": 315.7979,
+    "train_samples_per_second": 16.53,
+    "train_steps_per_second": 0.063
 }

trainer_state.json

@@ -1,142 +1,163 @@
 {
-  "best_metric": 0.9310344827586207,
-  "best_model_checkpoint": "segformer-class-classWeights-augmentation/checkpoint-40",
-  "epoch": 8.88888888888889,
-  "global_step": 60,
+  "best_metric": 0.7586206896551724,
+  "best_model_checkpoint": "segformer-class-classWeights-augmentation/checkpoint-15",
+  "epoch": 13.333333333333334,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.89,
-      "eval_accuracy": 0.5862068965517241,
-      "eval_loss": 1.0178804397583008,
-      "eval_runtime": 1.1426,
-      "eval_samples_per_second": 25.38,
-      "eval_steps_per_second": 2.626,
-      "step": 6
+      "epoch": 0.67,
+      "eval_accuracy": 0.3103448275862069,
+      "eval_loss": 1.2027289867401123,
+      "eval_runtime": 1.1652,
+      "eval_samples_per_second": 24.889,
+      "eval_steps_per_second": 0.858,
+      "step": 1
     },
     {
-      "epoch": 1.48,
-      "learning_rate": 4.62962962962963e-05,
-      "loss": 0.9897,
-      "step": 10
+      "epoch": 2.0,
+      "eval_accuracy": 0.3448275862068966,
+      "eval_loss": 1.121168851852417,
+      "eval_runtime": 0.8076,
+      "eval_samples_per_second": 35.908,
+      "eval_steps_per_second": 1.238,
+      "step": 3
     },
     {
-      "epoch": 1.93,
-      "eval_accuracy": 0.7241379310344828,
-      "eval_loss": 0.760027289390564,
-      "eval_runtime": 0.8084,
-      "eval_samples_per_second": 35.874,
-      "eval_steps_per_second": 3.711,
-      "step": 13
+      "epoch": 2.67,
+      "eval_accuracy": 0.41379310344827586,
+      "eval_loss": 1.0648072957992554,
+      "eval_runtime": 0.7994,
+      "eval_samples_per_second": 36.278,
+      "eval_steps_per_second": 1.251,
+      "step": 4
     },
     {
-      "epoch": 2.96,
-      "learning_rate": 3.7037037037037037e-05,
-      "loss": 0.5848,
-      "step": 20
+      "epoch": 4.0,
+      "eval_accuracy": 0.5172413793103449,
+      "eval_loss": 0.9779136776924133,
+      "eval_runtime": 1.1072,
+      "eval_samples_per_second": 26.193,
+      "eval_steps_per_second": 0.903,
+      "step": 6
     },
     {
-      "epoch": 2.96,
-      "eval_accuracy": 0.5862068965517241,
-      "eval_loss": 0.8368268609046936,
-      "eval_runtime": 1.6581,
-      "eval_samples_per_second": 17.49,
-      "eval_steps_per_second": 1.809,
-      "step": 20
+      "epoch": 4.67,
+      "eval_accuracy": 0.5517241379310345,
+      "eval_loss": 0.9493536353111267,
+      "eval_runtime": 0.8027,
+      "eval_samples_per_second": 36.129,
+      "eval_steps_per_second": 1.246,
+      "step": 7
     },
     {
-      "epoch": 4.0,
-      "eval_accuracy": 0.8620689655172413,
-      "eval_loss": 0.4708000719547272,
-      "eval_runtime": 0.8189,
-      "eval_samples_per_second": 35.414,
-      "eval_steps_per_second": 3.663,
-      "step": 27
+      "epoch": 6.0,
+      "eval_accuracy": 0.5862068965517241,
+      "eval_loss": 0.9168237447738647,
+      "eval_runtime": 0.8186,
+      "eval_samples_per_second": 35.426,
+      "eval_steps_per_second": 1.222,
+      "step": 9
     },
     {
-      "epoch": 4.44,
+      "epoch": 6.67,
       "learning_rate": 2.777777777777778e-05,
-      "loss": 0.2747,
-      "step": 30
+      "loss": 0.9535,
+      "step": 10
     },
     {
-      "epoch": 4.89,
-      "eval_accuracy": 0.896551724137931,
-      "eval_loss": 0.37271812558174133,
-      "eval_runtime": 0.8067,
-      "eval_samples_per_second": 35.951,
-      "eval_steps_per_second": 3.719,
-      "step": 33
+      "epoch": 6.67,
+      "eval_accuracy": 0.6551724137931034,
+      "eval_loss": 0.8808135390281677,
+      "eval_runtime": 1.1217,
+      "eval_samples_per_second": 25.853,
+      "eval_steps_per_second": 0.891,
+      "step": 10
     },
     {
-      "epoch": 5.93,
-      "learning_rate": 1.8518518518518518e-05,
-      "loss": 0.2259,
-      "step": 40
+      "epoch": 8.0,
+      "eval_accuracy": 0.7241379310344828,
+      "eval_loss": 0.8135725855827332,
+      "eval_runtime": 0.8159,
+      "eval_samples_per_second": 35.544,
+      "eval_steps_per_second": 1.226,
+      "step": 12
     },
     {
-      "epoch": 5.93,
-      "eval_accuracy": 0.9310344827586207,
-      "eval_loss": 0.3100181221961975,
-      "eval_runtime": 1.1422,
-      "eval_samples_per_second": 25.389,
-      "eval_steps_per_second": 2.626,
-      "step": 40
+      "epoch": 8.67,
+      "eval_accuracy": 0.7241379310344828,
+      "eval_loss": 0.8014845848083496,
+      "eval_runtime": 0.8311,
+      "eval_samples_per_second": 34.894,
+      "eval_steps_per_second": 1.203,
+      "step": 13
     },
     {
-      "epoch": 6.96,
-      "eval_accuracy": 0.9310344827586207,
-      "eval_loss": 0.22938820719718933,
-      "eval_runtime": 0.7944,
-      "eval_samples_per_second": 36.504,
-      "eval_steps_per_second": 3.776,
-      "step": 47
+      "epoch": 10.0,
+      "eval_accuracy": 0.7586206896551724,
+      "eval_loss": 0.7727243900299072,
+      "eval_runtime": 0.8049,
+      "eval_samples_per_second": 36.028,
+      "eval_steps_per_second": 1.242,
+      "step": 15
     },
     {
-      "epoch": 7.41,
-      "learning_rate": 9.259259259259259e-06,
-      "loss": 0.1596,
-      "step": 50
+      "epoch": 10.67,
+      "eval_accuracy": 0.7586206896551724,
+      "eval_loss": 0.7510485053062439,
+      "eval_runtime": 0.7895,
+      "eval_samples_per_second": 36.733,
+      "eval_steps_per_second": 1.267,
+      "step": 16
     },
     {
-      "epoch": 8.0,
-      "eval_accuracy": 0.896551724137931,
-      "eval_loss": 0.26314061880111694,
-      "eval_runtime": 1.212,
-      "eval_samples_per_second": 23.927,
-      "eval_steps_per_second": 2.475,
-      "step": 54
+      "epoch": 12.0,
+      "eval_accuracy": 0.7586206896551724,
+      "eval_loss": 0.6996777653694153,
+      "eval_runtime": 0.8164,
+      "eval_samples_per_second": 35.52,
+      "eval_steps_per_second": 1.225,
+      "step": 18
+    },
+    {
+      "epoch": 12.67,
+      "eval_accuracy": 0.7586206896551724,
+      "eval_loss": 0.6856328248977661,
+      "eval_runtime": 1.1618,
+      "eval_samples_per_second": 24.961,
+      "eval_steps_per_second": 0.861,
+      "step": 19
     },
     {
-      "epoch": 8.89,
+      "epoch": 13.33,
       "learning_rate": 0.0,
-      "loss": 0.1844,
-      "step": 60
-    },
-    {
-      "epoch": 8.89,
-      "eval_accuracy": 0.9310344827586207,
-      "eval_loss": 0.26064130663871765,
-      "eval_runtime": 0.8176,
-      "eval_samples_per_second": 35.469,
-      "eval_steps_per_second": 3.669,
-      "step": 60
-    },
-    {
-      "epoch": 8.89,
-      "step": 60,
-      "total_flos": 5.786635923932774e+16,
-      "train_loss": 0.40318952401479086,
-      "train_runtime": 239.9675,
-      "train_samples_per_second": 10.876,
-      "train_steps_per_second": 0.25
+      "loss": 0.5181,
+      "step": 20
+    },
+    {
+      "epoch": 13.33,
+      "eval_accuracy": 0.7586206896551724,
+      "eval_loss": 0.6802691221237183,
+      "eval_runtime": 1.6744,
+      "eval_samples_per_second": 17.32,
+      "eval_steps_per_second": 0.597,
+      "step": 20
+    },
+    {
+      "epoch": 13.33,
+      "step": 20,
+      "total_flos": 8.682439554251366e+16,
+      "train_loss": 0.735786771774292,
+      "train_runtime": 315.7979,
+      "train_samples_per_second": 16.53,
+      "train_steps_per_second": 0.063
     }
   ],
-  "max_steps": 60,
-  "num_train_epochs": 10,
-  "total_flos": 5.786635923932774e+16,
+  "max_steps": 20,
+  "num_train_epochs": 20,
+  "total_flos": 8.682439554251366e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28b1869361cd2514a9d7daa9fe27172273d61e7ea2f46240acdf40d502a06d64
+oid sha256:5666761ecbb085d38cf124e2c43db752708a3cf1af043ed922a9974d5caa4935
 size 4027